Skip to main content
Glama
Sign In
code-explorer

code-explorer

by vmikhailov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

check_semantic_gates

Evaluate Semantic Invariant Gate violations across a workspace or changed files, returning zero-match status, new versus tolerated debt, and remediation guidance for CI.

Instructions

Evaluate Semantic Invariant Gates (SIG) across the workspace or against specific changed files. Returns zero-match status, new vs tolerated violations, and remediation guidance.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_semantic_gates"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of violations or groups to return. Default: 50.
scopeNoOptional scope filter: 'Method', 'Class', 'Module', 'Service', 'System'.
gateIdNoOptional specific Gate ID to run (e.g. 'SIG-P-B-001').
groupByNoGroup violations summary by: 'file', 'symbol', or 'callee'.
categoryNoOptional category filter: 'Architectural' or 'Platform'.
platformNoOptional platform filter: e.g. 'agnostic', 'dotnet', 'typescript', 'python', 'go', 'java'.
dimensionNoOptional dimension filter: 'Contract', 'Rules', 'Resources', 'Boundaries'.
fileFilterNoFilter violations by file path substring.
workspacePathNoOptional workspace root path.
includeToleratedNoInclude tolerated baseline debt in results. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.80.5

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose the return payload (zero-match status, new vs. tolerated violations, remediation guidance), which is valuable. However, it never states whether evaluation is read-only, whether it mutates a baseline or workspace index, whether permissions/indexing are prerequisites, or anything about cost or duration for a workspace-wide run.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, zero filler: the action and its two scopes come first, and the second sentence is spent entirely on the return contract. Nothing needs to be moved or cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with no output schema and no annotations, the description covers the high-level output but leaves the tolerated/baseline workflow, the relationship between 'changed files' and fileFilter, and the meaning of scoping/grouping choices unexplained. It is adequate to fire the tool with defaults but not to use it confidently across its parameter space.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and every parameter carries its own descriptive text with enumerated values, so the baseline would be 3. The description adds a small amount beyond the schema by clarifying that evaluation can be narrowed to 'specific changed files', which helps map the intent onto the fileFilter parameter, though it does not explain limit, groupBy, or includeTolerated semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Evaluate Semantic Invariant Gates') plus the two evaluation modes (whole workspace vs. specific changed files), which is enough to know what it does. It stops short of differentiating itself from the sibling 'list_semantic_gates', so an agent cannot tell from the description alone which one lists definitions and which one runs checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'across the workspace or against specific changed files' implies the two contexts in which to use it, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many analysis siblings. An agent must infer that this is the gate-execution tool rather than the gate-listing tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools